The field of healthcare analytics is rapidly evolving, with a growing focus on the development of innovative AI-powered tools and techniques for improving disease diagnosis, patient outcomes, and clinical decision-making. Recent research has highlighted the importance of integrating semantic operations into SQL engines, enabling users to query both structured and unstructured data effortlessly. Additionally, there is a growing recognition of the need for robust methods, such as Propensity Score Matching, to achieve valid causal inference from administrative data in the absence of randomization. The use of large language models (LLMs) is also becoming increasingly prevalent in healthcare, with applications in medical emergency advising, disease diagnosis, and patient risk prediction. Noteworthy papers in this area include: MIMIC-SR-ICD11, which introduces a large English diagnostic dataset built from EHR discharge notes and presents a likelihood-based re-ranking framework for disease diagnosis. Cortex AISQL, which integrates native semantic operations directly into SQL, allowing users to write declarative queries that combine relational operations with semantic reasoning. A Super-Learner with Large Language Models for Medical Emergency Advising, which builds a super-learner that produces higher diagnostic accuracy by integrating a cluster of LLMs using a meta-learner. Data reuse enables cost-efficient randomized trials of medical AI models, which proposes a data-reuse RCT design for AI-based risk models, reducing the enrollment requirement for subsequent trials and saving costs.